计算机工程与应用
計算機工程與應用
계산궤공정여응용
COMPUTER ENGINEERING AND APPLICATIONS
2013年
24期
138-143
,共6页
镜头边界检测%H.264压缩域%不平衡支持向量机
鏡頭邊界檢測%H.264壓縮域%不平衡支持嚮量機
경두변계검측%H.264압축역%불평형지지향량궤
shot boundary detection%H.264 compressed domain%biased Support Vector Machine(SVM)
为了直接从H.264码流中检测镜头边界,提出了利用H.264压缩域多特征和Biased-SVM(不平衡支持向量机)分类算法的检测方法。分析帧类型、宏块类型、运动矢量、帧内预测模式等信息,以获得发生镜头突变和渐变的特征。针对镜头边界帧的数量远少于视频帧总数的特点,用Biased-SVM分类方法将视频帧分为突变帧、渐变帧和非镜头边界帧。在TRECVID视频集上的实验结果表明,与其他H.264压缩域的算法相比,该算法有更好的性能。
為瞭直接從H.264碼流中檢測鏡頭邊界,提齣瞭利用H.264壓縮域多特徵和Biased-SVM(不平衡支持嚮量機)分類算法的檢測方法。分析幀類型、宏塊類型、運動矢量、幀內預測模式等信息,以穫得髮生鏡頭突變和漸變的特徵。針對鏡頭邊界幀的數量遠少于視頻幀總數的特點,用Biased-SVM分類方法將視頻幀分為突變幀、漸變幀和非鏡頭邊界幀。在TRECVID視頻集上的實驗結果錶明,與其他H.264壓縮域的算法相比,該算法有更好的性能。
위료직접종H.264마류중검측경두변계,제출료이용H.264압축역다특정화Biased-SVM(불평형지지향량궤)분류산법적검측방법。분석정류형、굉괴류형、운동시량、정내예측모식등신식,이획득발생경두돌변화점변적특정。침대경두변계정적수량원소우시빈정총수적특점,용Biased-SVM분류방법장시빈정분위돌변정、점변정화비경두변계정。재TRECVID시빈집상적실험결과표명,여기타H.264압축역적산법상비,해산법유경호적성능。
In order to detect shot boundaries in H.264 bit streams, a shot boundary detection method using compressed domain features of H.264 and Biased-SVM(Biased Support Vector Machine)is proposed. The features about the abrupt shot changes and gradual shot changes are obtained by analyzing the information of frame type, macroblock type, motion vector, intra-prediction mode, etc. As the number of shot boundary frames is far fewer than the total number of video frames, proposed method chooses Biased-SVM to classify the frames into three classes, namely, the frames of abrupt change, gradual change and non-change. Experi-mental results on TRECVID video dataset indicate that the presented approach has better performance on shot boundary detection, compared with other method in H.264 compressed domain.